Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 834 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.6213. Min Act: -0.1700

Data Index: 1025189 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.6057. Min Act: -0.1700

Data Index: 772131 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.5900. Min Act: -0.1700

Data Index: 237020 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.4803. Min Act: -0.1700

Data Index: 808073 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.4647. Min Act: -0.1700

Data Index: 467252 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.4490. Min Act: -0.1700

Data Index: 1010649 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.4176. Min Act: -0.1700

Data Index: 443299 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.3863. Min Act: -0.1700

Data Index: 1337222 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.3706. Min Act: -0.1700

Data Index: 663501 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.3549. Min Act: -0.1700

Data Index: 76881 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.3235. Min Act: -0.1700

Data Index: 858421 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.3078. Min Act: -0.1700

Data Index: 1308647 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.3392. Min Act: -0.1700

Data Index: 873829 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.3235. Min Act: -0.1700

Data Index: 187481 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.2921. Min Act: -0.1700

Data Index: 988952 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.3078. Min Act: -0.1700

Data Index: 1218439 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.3078. Min Act: -0.1700

Data Index: 579849 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.2921. Min Act: -0.1700

Data Index: 332501 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.2764. Min Act: -0.1700

Data Index: 87836 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 3.6213. Min Range: -3.6213

Max Act: 3.2764. Min Act: -0.1700

Data Index: 79011 (C4 (Web Text))

Max Activating Token Index: 960